Value Iteration is Optic Composition

DOI10.4204/eptcs.380.24arXiv2206.04547MaRDI QIDQ6190614

Unnamed Author, Jules Hedges

Publication date: 5 March 2024

Published in: Electronic Proceedings in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2206.04547

Mathematics Subject Classification ID

Computer science (68-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Long-term values in Markov decision processes, (co)algebraically
• \({\mathcal Q}\)-learning
• Morphisms of open games
• A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics
• Optimal control of Markov processes with incomplete state information
• (Co)end Calculus
• A Probability Monad as the Colimit of Spaces of Finite Samples
• Double Categories of Open Dynamical Systems (Extended Abstract)
• Compositional Game Theory
• Categories in Control
• Contraction Mappings in the Theory Underlying Dynamic Programming
• Closed categories generated by commutative monads